toneden-automation

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References external documentation and MCP server endpoints from well-known technology services including Composio (composio.dev) and Rube (rube.app).
  • [COMMAND_EXECUTION]: Outlines instructions for using the Rube MCP toolset to manage authentication and execute automated workflows via specific tool slugs.
  • [PROMPT_INJECTION]: The skill involves processing tool schemas and search results at runtime which constitutes a potential indirect prompt injection surface; however, the skill itself contains no malicious instructions and uses standard discovery patterns.
  • Ingestion points: Tool schemas and execution plans returned by RUBE_SEARCH_TOOLS.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Subprocess execution via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.
  • Sanitization: None specified in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 04:37 PM
Security Audit — agent-trust-hub — toneden-automation